Agentic AI Engineering with Python — Build Autonomous Agents Training Course

Foundations of Agentic AI

• Defining autonomous agents: core concepts and classification
• The agent cycle: the loop of perception, decision-making, action, and observation
• Establishing design patterns for agent responsibilities and operational scope

Python Ecosystem and Agent SDKs

• Leveraging frameworks like LangChain to initialize agents
• Asynchronous programming, task queuing, and subprocess handling
• Code packaging, virtual environments, and reproducible development practices

Integration of External Tools and APIs

• Creating tool interfaces and secure invocation patterns
• Connecting agents to web services, databases, and internal applications
• Managing credentials, secrets, and enforcing least-privilege access

Memory, State, and Context Handling

• Short-term context windows and advanced prompt engineering methods
• Long-term memory structures: utilizing Redis, vector databases, and retrieval augmentation
• Ensuring data consistency, implementing caching, and maintaining memory hygiene

Orchestration, Planning, and Multi-Step Processes

• Linking actions, managing subagents, and decomposing complex tasks
• Comparing planning algorithms with heuristic orchestration approaches
• Managing errors, implementing retries, and executing compensating actions

Safety, Validation, and Observability

• Developing threat models, conducting red-teaming, and sanitizing inputs and outputs
• Performing unit, integration, and end-to-end testing for agent systems
• Implementing logging, metrics, tracing, and alerting for agent performance

Deployment, Scaling, and Agent MLOps

• Containerization strategies, CI/CD pipeline integration, and deployment plans
• Controlling costs, applying rate limits, and optimizing resource usage
• Establishing monitoring systems, governance structures, and operational guidelines

Recap and Future Directions